Model Description
v1.0 aims for the highest fidelity to the official design.
This LoRA is a character enhancement model for Nefarith (聂菲斯 / ネファリス) from Arknights: Endfield, fine-tuned on a dataset of 400+ images. It can recreate Nefarith using the trigger word Nefarith alone.
In addition to LoRA based on IllustriouxXL, I have also trained versions based on NoobAI, AnimagineXL, PonyXL, WAI-IllustriousXL. Comming soon.
Recommended Settings
Recommended weight: 0.9 - 1.0
example prompt :(Please adjust the prompts according to model card of the checkpoint you are using.)
masterpiece, best quality, amazing quality, 1girl, Nefarith, solo, upper body, standing, looking at viewer, smile, simple bakcground, dark, detailed light,full body:
masterpiece, best quality, amazing quality, 1girl, Nefarith, solo, tail, standing, looking at viewer, smile, full body, simple bakcground, dark, detailed light,For full-body shots, you can try adding full body and tail.
Others
While I am satisfied with the fidelity of features like her breastplate, headwear, and tail...please feel free to leave your generations or feedback.
Thank you for your support!
模型简介
v1.0 追求在官方服设下的最高还原度。
这个LoRA模型是角色伊冯（明日方舟：终末地）的角色增强模型，在300+ 张图片的数据集微调得到。此LoRA使用触发词Yvonne即可还原人物，也提供了可拆卸的服装提示词，方便各类二创发挥。
除了基于Illustrious XL的版本，我还训练了基于NoobAI，AnimagineXL，PonyXL，WAI-IllustriousXL的版本，coming soon 。
推荐设置
推荐权重： 0.9 - 1.0
（请根据你实际使用的Checkpoint模型的官方文档，适当调整提示词策略。）
示例prompt:
masterpiece, best quality, amazing quality, 1girl, Nefarith, solo, upper body, standing, looking at viewer, smile, simple bakcground, dark, detailed light,全身:
masterpiece, best quality, amazing quality, 1girl, Nefarith, solo, tail, standing, looking at viewer, smile, full body, simple bakcground, dark, detailed light,全身可尝试添加full body, tail 等。
小记
虽然我已经对她的特征还原程度很满意，包括胸甲，头饰，尾巴等等，但如果有任何反馈意见欢迎评论，以便我做出调整，谢谢。我会定期在社交媒体发布图片，可在对应平台取原图。
Bilibili账号：https://space.bilibili.com/12595237?spm_id_from=333.1007.0.0
小红书账号：https://www.xiaohongshu.com/user/profile/68483ecb000000001b019555